← Back to PeopleMSResearcherMadhuri ShanbhogueGoogleLinkedInLead author of Gemini Embedding 2, a unified multimodal embedding model for video, audio, image and text.1Mentions1Articles1OutletsCompanies CoveredGoogle DeepMind1ArticlesMost recent firstMentioned InReferenced in coverageGoogle DeepMind releases one embedding model for text, audio, video, and imagesarXivpositiveMay 28, 2026“Lead author of Gemini Embedding 2, a unified multimodal embedding model for video, audio, image and text.”